Tensor Train decomposition on TensorFlow (T3F)
arXiv:1801.01928
Abstract
Tensor Train decomposition is used across many branches of machine learning. We present T3F -- a library for Tensor Train decomposition based on TensorFlow. T3F supports GPU execution, batch processing, automatic differentiation, and versatile functionality for the Riemannian optimization framework, which takes into account the underlying manifold structure to construct efficient optimization methods. The library makes it easier to implement machine learning papers that rely on the Tensor Train decomposition. T3F includes documentation, examples and 94% test coverage.
References in corpus (6)
- A Spectral Algorithm for Latent Dirichlet Allocation
- Long-term Forecasting using Higher Order Tensor RNNs
- Open source Matrix Product States: Opening ways to simulate entangled many-body quantum systems in one dimension
- Tensor-Train Recurrent Neural Networks for Video Classification
- Low-rank Riemannian eigensolver for high-dimensional Hamiltonians
- Expressive power of recurrent neural networks
Cited by in corpus (9)
- Tensor Methods in Computer Vision and Deep Learning
- Compressing 3DCNNs Based on Tensor Train Decomposition
- Quantum State Tomography for Matrix Product Density Operators
- Low-rank Riemannian eigensolver for high-dimensional Hamiltonians
- Optimizing Tensor Train Decomposition in DNNs for RISC-V Architectures Using Design Space Exploration and Compiler Optimizations
- PASTA: A Parallel Sparse Tensor Algorithm Benchmark Suite
- HOTTBOX: Higher Order Tensor ToolBOX
- Patch-based Medical Image Segmentation using Matrix Product State Tensor Networks
- Training Neural Machine Translation (NMT) Models using Tensor Train Decomposition on TensorFlow (T3F)